DeMAAE: deep multiplicative attention-based autoencoder for identification of peculiarities in video sequences.
Nazia AslamMaheshkumar H. KolekarPublished in: Vis. Comput. (2024)
Keyphrases
- video sequences
- frame rate
- video data
- image sequences
- automatic identification
- motion estimation
- space time
- multi view
- inter frame
- visual attention
- video segmentation
- object tracking
- focus of attention
- deep learning
- video shots
- face tracking
- data sets
- visual tracking
- temporal information
- unsupervised learning
- high speed
- computational complexity
- computer vision
- learning algorithm